gh-139109: A new tracing JIT compiler frontend for CPython

.github/workflows/jit.yml

@@ -57,9 +57,10 @@ jobs:
       fail-fast: false
       matrix:
         target:
-          - i686-pc-windows-msvc/msvc
-          - x86_64-pc-windows-msvc/msvc
-          - aarch64-pc-windows-msvc/msvc
+# To re-enable later when we support these.
+#          - i686-pc-windows-msvc/msvc
+#          - x86_64-pc-windows-msvc/msvc
+#          - aarch64-pc-windows-msvc/msvc
           - x86_64-apple-darwin/clang
           - aarch64-apple-darwin/clang
           - x86_64-unknown-linux-gnu/gcc
@@ -70,15 +71,16 @@ jobs:
         llvm:
           - 19
         include:
-          - target: i686-pc-windows-msvc/msvc
-            architecture: Win32
-            runner: windows-2022
-          - target: x86_64-pc-windows-msvc/msvc
-            architecture: x64
-            runner: windows-2022
-          - target: aarch64-pc-windows-msvc/msvc
-            architecture: ARM64
-            runner: windows-11-arm
+# To re-enable later when we support these.
+#          - target: i686-pc-windows-msvc/msvc
+#            architecture: Win32
+#            runner: windows-2022
+#          - target: x86_64-pc-windows-msvc/msvc
+#            architecture: x64
+#            runner: windows-2022
+#          - target: aarch64-pc-windows-msvc/msvc
+#            architecture: ARM64
+#            runner: windows-11-arm
           - target: x86_64-apple-darwin/clang
             architecture: x86_64
             runner: macos-15-intel

Include/internal/pycore_backoff.h

@@ -99,7 +99,12 @@ backoff_counter_triggers(_Py_BackoffCounter counter)
 // Must be larger than ADAPTIVE_COOLDOWN_VALUE, otherwise when JIT code is
 // invalidated we may construct a new trace before the bytecode has properly
 // re-specialized:
-#define JUMP_BACKWARD_INITIAL_VALUE 4095
+// Note: this should be a prime number-1. This increases the likelihood of
+// finding a "good" loop iteration to trace.
+// For example, 4095 does not work for the nqueens benchmark on pyperformance
+// as we always end up tracing the loop iteration's
+// exhaustion iteration. Which aborts our current tracer.
+#define JUMP_BACKWARD_INITIAL_VALUE 4000
 #define JUMP_BACKWARD_INITIAL_BACKOFF 12
 static inline _Py_BackoffCounter
 initial_jump_backoff_counter(void)
@@ -112,7 +117,7 @@ initial_jump_backoff_counter(void)
  * Must be larger than ADAPTIVE_COOLDOWN_VALUE,
  * otherwise when a side exit warms up we may construct
  * a new trace before the Tier 1 code has properly re-specialized. */
-#define SIDE_EXIT_INITIAL_VALUE 4095
+#define SIDE_EXIT_INITIAL_VALUE 4000
 #define SIDE_EXIT_INITIAL_BACKOFF 12
 
 static inline _Py_BackoffCounter
@@ -129,6 +134,14 @@ initial_unreachable_backoff_counter(void)
     return make_backoff_counter(0, UNREACHABLE_BACKOFF);
 }
 
+// Required to not get stuck in infinite specialization loops due to specialization failure.
+// We use 2 here as there are a few scenarios:
+// 1. Freshly specialized from unspecialized, in which case the counter will be 1.
+// 2. Re-specialized from deopt, in which case the counter will be 1.
+// 3. Deopt -> Specialize -> Deopt -> Specialize, in which case the counter will be 2.
+// We do not want the 3rd case.
+#define MAX_SPECIALIZATION_TRIES 2
+
 #ifdef __cplusplus
 }
 #endif

Include/internal/pycore_ceval.h

@@ -392,6 +392,8 @@ _PyForIter_VirtualIteratorNext(PyThreadState* tstate, struct _PyInterpreterFrame
 #define SPECIAL___AEXIT__   3
 #define SPECIAL_MAX   3
 
+PyAPI_DATA(const _Py_CODEUNIT *) _Py_INTERPRETER_TRAMPOLINE_INSTRUCTIONS_PTR;
+
 #ifdef __cplusplus
 }
 #endif

Include/internal/pycore_interp_structs.h

@@ -14,8 +14,6 @@ extern "C" {
 #include "pycore_structs.h"       // PyHamtObject
 #include "pycore_tstate.h"        // _PyThreadStateImpl
 #include "pycore_typedefs.h"      // _PyRuntimeState
-#include "pycore_uop.h"           // struct _PyUOpInstruction
-
 
 #define CODE_MAX_WATCHERS 8
 #define CONTEXT_MAX_WATCHERS 8
@@ -757,6 +755,7 @@ struct _Py_unique_id_pool {
 
 typedef _Py_CODEUNIT *(*_PyJitEntryFuncPtr)(struct _PyExecutorObject *exec, _PyInterpreterFrame *frame, _PyStackRef *stack_pointer, PyThreadState *tstate);
 
+
 /* PyInterpreterState holds the global state for one of the runtime's
    interpreters.  Typically the initial (main) interpreter is the only one.
 
@@ -934,10 +933,10 @@ struct _is {
     PyObject *common_consts[NUM_COMMON_CONSTANTS];
     bool jit;
     bool compiling;
-    struct _PyUOpInstruction *jit_uop_buffer;
     struct _PyExecutorObject *executor_list_head;
     struct _PyExecutorObject *executor_deletion_list_head;
     struct _PyExecutorObject *cold_executor;
+    struct _PyExecutorObject *cold_dynamic_executor;
     int executor_deletion_list_remaining_capacity;
     size_t executor_creation_counter;
     _rare_events rare_events;